Index: lib/Transforms/InstCombine/InstCombineCalls.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -182,8 +182,6 @@
     return MI;
   }
 
-  // If MemCpyInst length is 1/2/4/8 bytes then replace memcpy with
-  // load/store.
   ConstantInt *MemOpLength = dyn_cast<ConstantInt>(MI->getArgOperand(2));
   if (!MemOpLength) return nullptr;
 
@@ -194,8 +192,16 @@
   uint64_t Size = MemOpLength->getLimitedValue();
   assert(Size && "0-sized memory transferring should be removed already.");
 
-  if (Size > 8 || (Size&(Size-1)))
-    return nullptr;  // If not 1/2/4/8 bytes, exit.
+
+  // Since we don't have perfect knowledge here, make some assumptions: assume
+  // the maximum allowed stores for memcpy operation is the same size as the 
+  // largest legal integer size. 
+  unsigned LargestInt = DL.getLargestLegalIntTypeSizeInBits();
+  if (LargestInt == 0)
+    LargestInt = 32;
+
+  if (Size > 2*LargestInt/8 || (Size&(Size-1)))
+    return nullptr;  
 
   // Use an integer load+store unless we can find something better.
   unsigned SrcAddrSp =
Index: output_bultin_memcpy_patterns.ll
===================================================================
--- output_bultin_memcpy_patterns.ll
+++ output_bultin_memcpy_patterns.ll
@@ -8,7 +8,10 @@
 ; Function Attrs: nounwind uwtable
 define void @foo(i8* %a, i8* %b) local_unnamed_addr #0 {
 entry:
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %a, i8* %b, i64 16, i32 1, i1 false)
+  %0 = bitcast i8* %b to i128*
+  %1 = bitcast i8* %a to i128*
+  %2 = load i128, i128* %0, align 1
+  store i128 %2, i128* %1, align 1
   ret void
 }
 
@@ -55,10 +58,11 @@
   %mul = shl nsw i32 %i.0, 2
   %idx.ext = sext i32 %mul to i64
   %add.ptr = getelementptr inbounds i32, i32* %a, i64 %idx.ext
-  %0 = bitcast i32* %add.ptr to i8*
   %add.ptr3 = getelementptr inbounds [16 x i32], [16 x i32]* @b, i64 0, i64 %idx.ext
-  %1 = bitcast i32* %add.ptr3 to i8*
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* %1, i64 16, i32 4, i1 false)
+  %0 = bitcast i32* %add.ptr3 to i128*
+  %1 = bitcast i32* %add.ptr to i128*
+  %2 = load i128, i128* %0, align 16
+  store i128 %2, i128* %1, align 4
   %inc = add nsw i32 %i.0, 1
   br label %for.cond
 
Index: test/DebugInfo/X86/array2.ll
===================================================================
--- test/DebugInfo/X86/array2.ll
+++ test/DebugInfo/X86/array2.ll
@@ -53,7 +53,7 @@
   call void @llvm.dbg.declare(metadata i8*** %argv.addr, metadata !25, metadata !DIExpression()), !dbg !24
   call void @llvm.dbg.declare(metadata [4 x i32]* %array, metadata !26, metadata !DIExpression()), !dbg !30
   %0 = bitcast [4 x i32]* %array to i8*, !dbg !30
-  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast ([4 x i32]* @main.array to i8*), i64 16, i32 16, i1 false), !dbg !30
+  call void @llvm.memcpy.p0i8.p0i8.i64(i8* %0, i8* bitcast ([4 x i32]* @main.array to i8*), i64 128, i32 16, i1 false), !dbg !30
   %arraydecay = getelementptr inbounds [4 x i32], [4 x i32]* %array, i32 0, i32 0, !dbg !31
   call void @f(i32* %arraydecay), !dbg !31
   %arrayidx = getelementptr inbounds [4 x i32], [4 x i32]* %array, i32 0, i64 0, !dbg !32